WO2020178091A1 - Système et procédé de découverte et d'identification de nœuds de calcul dans un réseau - Google Patents

Système et procédé de découverte et d'identification de nœuds de calcul dans un réseau Download PDF

Info

Publication number
WO2020178091A1
WO2020178091A1 PCT/EP2020/054978 EP2020054978W WO2020178091A1 WO 2020178091 A1 WO2020178091 A1 WO 2020178091A1 EP 2020054978 W EP2020054978 W EP 2020054978W WO 2020178091 A1 WO2020178091 A1 WO 2020178091A1
Authority
WO
WIPO (PCT)
Prior art keywords
probe
computing nodes
planning module
software application
workload
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/EP2020/054978
Other languages
German (de)
English (en)
Inventor
Ludwig Andreas MITTERMEIER
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Siemens Corp
Original Assignee
Siemens AG
Siemens Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG, Siemens Corp filed Critical Siemens AG
Priority to CN202080018594.2A priority Critical patent/CN113518974B/zh
Priority to US17/435,815 priority patent/US11669373B2/en
Publication of WO2020178091A1 publication Critical patent/WO2020178091A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • G06F11/3433—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment for load management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/501—Performance criteria
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/5015—Service provider selection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/508—Monitor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/54—Indexing scheme relating to G06F9/54
    • G06F2209/549—Remote execution

Definitions

  • the invention relates to a system and method for locating and identifying computational nodes in a network.
  • Fog computing or fog networking also known as fogging, is an architecture that uses edge devices to perform a significant portion of the computation, storage, communication locally and over the Internet backbone.
  • cloud computing and fog computing provide storage, applications and data for end users and industrial users.
  • fog computing is closer to the end users and more geographically distributed.
  • Fog computing involves the distribution of communications, computation, and storage resources and services on or near devices and systems that control end users. Fog computing is not a substitute, but often a supplement to cloud computing.
  • Manufacturing machines such as CNC machines.
  • suitable computing nodes have been identified by manually defining the properties of the computing nodes and the workload characteristics by developers and operating personnel.
  • a processing system identifies suitable compute nodes for a given workload based on the properties of the compute nodes, recognizing either a subset or the entire set of properties and capabilities of the compute nodes. If a calculation node was found for a calculation task, this calculation node is also used. However, it is not checked whether there are possibly more suitable computing nodes available in order to optimize the utilization of the entire network or computing cluster and / or to achieve better or faster processing for a particular workload.
  • the document US 2014/196054 A1 describes a method for issuing a command for carrying out shortened power measurements for one or more computer nodes in order to determine whether a number of one or more computing nodes is sufficient on which a calculation can be carried out .
  • the document US 2018/129495 A1 describes a method for managing software.
  • a manager sends a request with a specific requirement, which is used to determine an optimal computer device for running the software. After selecting the optimal computing device, the software is sent to the selected computing device for editing.
  • the object on which the invention is based now consists in developing a system and a method for reliable
  • the invention relates to a system for finding and identifying computation nodes in a network with the features of claim 1.
  • the probe is integrated into the software application, and the planning module is suitable for sending the software application with the probe to the computing nodes. If the probe determines the suitability of a computational node, the software application can be started immediately.
  • the probe is designed to be independent of the software application and the planning module is suitable for only sending the probe to the computing nodes. This means that the probe can be sent to the various computing nodes more quickly, since it is not connected to the software application.
  • the probe advantageously contains a classification scheme with different categories for classifying the computation nodes, and the probe is designed to test the computation nodes using this classification scheme.
  • the probe has a cleaning component for removing artifacts on the computing nodes.
  • the test code is advantageously designed to test the computing nodes within 10-100 milliseconds.
  • the planning module is suitable for processing different software applications based on the test results of the probe for the workload of the different software applications in an optimized sequence using different computing nodes.
  • the invention relates to a method for locating and identifying computing nodes in a network with the features of claim 7.
  • the probe is integrated into the software application, and the planning module sends the software application with the probe to the computing node. If the probe determines the suitability of a computational node, the software application can be started immediately.
  • the probe is designed to be independent of the software application and the planning module only sends the probe to the computing nodes.
  • the probe advantageously contains a classification scheme with different categories for the classification of the computing nodes and the probe tests the computing nodes using this classification scheme. This enables the tested computation nodes to be quickly classified in a classification scheme.
  • the probe has a cleaning component for removing artifacts on the computing nodes.
  • the test code advantageously tests the computing nodes within 10-100 milliseconds.
  • the planning module is suitable for processing different software applications based on the test results of the probe for the workload of the different software applications in an optimized sequence using different computing nodes.
  • the invention relates to a
  • Computer program product comprising one and / or more executable computer codes which are designed for this
  • FIG. 1 shows an overview to explain a system according to the invention
  • FIG. 2 is a block diagram to explain a
  • FIG. 3 shows a block diagram to explain a further optional embodiment detail of the system according to the invention.
  • FIG. 4 shows a block diagram to explain a further optional embodiment detail of the system according to the invention.
  • FIG. 5 shows a flow chart to explain a method according to the invention
  • Figure 6 is a schematic representation of a
  • Fig. 1 shows a system 100 for the identification and selection of computing nodes 220, 240, 260, ..., N in a network 200, the computing nodes 220, 240, 260, ..., N are shown here only by way of example.
  • the computing nodes 220, 240, 260, ..., N can be of any size.
  • the computing nodes 220, 240, 260, ..., N can include edge devices (edge devices) with computer services, routers, sensors with software modules, communication interfaces or they can also be actuators, control devices or other hardware devices that are connected to the required computing power.
  • the computing nodes 220, 240, 260,..., N are networked with one another by means of communication connections 600 and can also be connected with one another by means of a cloud computing system, not shown here.
  • the network 200 can also represent an industrial plant and / or a unit such as, for example, a building complex that is monitored with at least some of the computing nodes 220, 240, 260,..., N. So some of the compute nodes 220, 240, 260, ..., N may e.g. Represent temperature sensors and smoke alarm sensors that monitor rooms in a building.
  • the computing nodes 220, 240, 260,... N receive or generate data and process them using software applications for specific applications.
  • the software applications can be loaded temporarily in accordance with a particular task or they are permanently stored in memory units in the respective computing nodes 220, 240, 260,..., N.
  • a planning module 300 for processing a software application 400 is provided in the network 200, which is connected to the various computing nodes 220, 240, 260,..., N.
  • the software application 400 is not processed in the planning module 300 itself, but in one of the computing nodes 220, 240, 260, ..., N in the network 200.
  • a suitable computing node N must be identified that is responsible for the processing the software application 400 performs.
  • a relevant criterion for the identification of suitable computing nodes N for a computational workload of a software application 400 can be the processor architecture of a computing node N, such as whether it is an ARM or x86_64 processor, since the computation commands must match the respective workload.
  • the size of the free main memory, the size of the free memory space, the degree of CPU utilization and / or the quality and the current status of the network connectivity of the computing node N, such as the bandwidth and the latency are indicators for selecting a computing node N.
  • the real-time properties of the computing node N and its operating system and the specific hardware that is connected to the computing node N, such as sensors and actuators, can play a role.
  • the planning module 300 is Darge in more detail. It preferably contains a processor 320 and a memory element 340 in which the software application 400 and / or the binary workload are stored.
  • the software application 400 and / or the binary workload (workload) is provided with a probe 500.
  • the probe 500 is designed as software code and contains a test code 550, which has the following properties:
  • the test code 550 can be started in a very short time, for example within a few milliseconds to seconds, since it has a short code length, and is in the network 200 fed to the properties of possible computing node N to test.
  • the code length can be very short and include, for example, 10-20 lines, but several hundred code lines can also be provided.
  • the test code 550 then independently suggests a computing node N or several computing nodes N in the network N on which the software application 400 can be executed.
  • criteria such as a low impact on CPU performance, memory consumption and network traffic are used.
  • the probe 500 also tests the availability of the required resources for a specific workload of the software application 400 in the network 200. If the resources are fundamentally not available, this is communicated by means of a message to a communication center not shown here.
  • the checking of the resources in the network 200 is advantageously concluded very quickly, for example within a few milliseconds to a few seconds. In individual cases, however, it can take a few minutes.
  • the probe 500 has a cleaning component 570 for cleaning the computing node N, so that no artifacts remain on the computing node N on which the test with the probe 500 is carried out.
  • This can be, for example, software libraries, memory entries and / or configuration files. If the probe 500 indicates a positive result, this means that a computing node N is suitable for a specific computing load by a software application 400.
  • the probe 500 can also store or leave codes etc. on the computing node 400, which are required for processing the software application on the computing node N or are necessary for planning a later processing on the computing node N.
  • the probe 500 can be present directly in the software application 400 and also the same Have data format, so that the probe 500 is sent into the network 200 together with the software application 400.
  • an implementation according to the invention can also take place in such a way that the probe 500 with the test code 550 from the real binary code of the workload of the software application 400 is separated. This is shown in FIG. 4. Since the test code 550 is in the form of a small software element, it can be distributed in the network 200 with little effort, and the binary code for a large workload is only provided for the computing nodes N that have a positive result in the execution of the test code 550 showed.
  • the probe 500 or test code 550 can be expanded by a classification scheme.
  • the probe 500 can contain classification parameters or categories in order to be able to use them for various software applications 400 that differ in terms of the computing power required for the processing. Examples of classification parameters can be:
  • a computing node N must have at least a certain number of freely available (main) storage space
  • a computing node N must have a certain hardware feature such as a real-time clock
  • a computing node must be connected to certain hardware such as a sensor.
  • the planning module 300 sends the probe 500 to the computing nodes 220, 240, 260,..., N in the network 200.
  • the test code 550 or the probe 500 communicates the test results to the planning module 300.
  • the test results contain in particular the information about the status of the computing node N, but can also include further information.
  • Functional elements are preferably provided in the planning module 300, which are called up by the text code 550 according to the respective test result, so that the planning module 300 receives knowledge of the test results through these function calls.
  • planning module 300 checks whether the processing fits into one or more processing categories for which tests have already been carried out by probe 500 in network 200 according to the established classification parameters of the probe 500.
  • Processing or processing of a software application may require the following requirements: At least one dual-core processor is required for a computing node N and 256 MB of storage capacity are required with a free main memory and 1 GB storage capacity required with free hard disk space.
  • a previously performed test using the probe 500 has possibly identified suitable computation nodes N with the following specifications: There is at least one quad-core processor, 512 MB storage capacity with a free working memory and 1 GB storage capacity with a free hard disk storage.
  • the planning module 300 could plan the new computing load without a new probe 500 having to be sent into the network 200. if the However, if the computing power required does not fit into one of the categories for which a test was previously carried out using the probe 500, the planning module 300 again carries out a test with regard to the computing power available at the computing nodes N in the network 200.
  • the planning module 300 preferably only carries out the workload test on computing nodes N that fall into the category that has already been classified.
  • a probe 500 is used to carry out tests relating to the processing capacities of computing nodes N for a workload, the computing nodes N being arranged in a heterogeneous network 200 and having different properties and workloads.
  • a classification scheme for a workload is provided, which simplifies the planning of the processing of a software application at various computing nodes N.
  • Unsuitable computing nodes N lead to a load on the network 200 and to additional work until a suitable computing node N can be identified for a workload.
  • the inadvertent execution of a workload on an unsuitable computing node N can also lead to damage, since, for example, a real-time task on a computing node N is negatively influenced if it is already busy with another computing task.
  • the probe 500 offers the possibility of quickly and with little effort, suitable computing nodes N for an ar- reliable to find payload.
  • the overall utilization of the network 200 is optimized by classifying workloads and documenting the test results for different workload categories. This documentation is preferably stored in the planning module 300.
  • the probe 500 with the test code 550 can be sent only to a selection of computing nodes N which, for example, have already been defined by developers and operators.
  • the planning module 300 then carries out an assignment between the predetermined computing nodes N and the workload categories and the workload is only carried out on the computing nodes N that are taken into account on the basis of this assignment.
  • FIG. 5 shows a flowchart of a method according to the invention for identifying computing nodes N for processing a workload in a network 200.
  • the planning module 300 sends a probe 500 to computing nodes 220, 240, 260, ..., N of the network 200, the probe 500 sending a test code 550 for testing the properties of the computing nodes 220, 240, 260, .. ., N contains.
  • test code 550 of the probe 500 tests the properties of the computing nodes 220, 240, 260,..., N with regard to their ability to process a specific workload of at least one software application 400.
  • test code 550 communicates the test results to the planning module 300.
  • the planning module 300 selects one or more computing nodes N for processing a workload of at least one software application 400 on the basis of the test results of the test code 550.
  • the planning module 300 starts the processing of the workload of the at least one software application 400 on the selected computing node N.
  • FIG. 6 schematically shows a computer program product 700 that contains one and / or more executable computer codes 750 that are implemented (are) to carry out (eg by a computer) a method according to an embodiment of the first aspect of the invention.
  • an identification of suitable computing nodes N for a specific workload of a software application in a network 200 consisting of computing nodes 220, 240, 260,..., N can be carried out.
  • computing nodes N in the network 200 can be specifically selected which are suitable for processing a workload, and an overload of the network 200 can thus be avoided.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Computer Hardware Design (AREA)
  • Debugging And Monitoring (AREA)

Abstract

La présente invention a trait à un système (100) de découverte et d'identification de nœuds de calcul (N) dans un réseau (200). Le système (100) se compose d'un réseau (200) ayant plusieurs nœuds de calcul (220, 240, 260, ..., Z), qui sont reliés entre eux au moyen de liaisons de communication (600) et sont conçus pour traiter une charge de travail d'une ou de plusieurs applications logicielles (400), et d'au moins un module de planification (300). Le module de planification (300) contient au moins une sonde (500) avec un code de test (550) et est conçu pour envoyer la sonde (500) avec le code de test (550) aux nœuds de calcul (220, 240, 260, ..., N) du réseau (200) pour tester les propriétés des nœuds de calcul (220, 240, 260, ..., N). Le code de test (550) est conçu pour tester les propriétés des nœuds de calcul (220, 240, 260, ..., N) en ce qui concerne leur aptitude à traiter une certaine charge de travail d'une application logicielle (400) et à communiquer les résultats des tests au module de planification (300). Le module de planification (300) est conçu pour sélectionner, en raison des résultats des tests du code de test (550), un ou plusieurs nœuds de calcul (N) pour le traitement d'au moins une application logicielle (400) et pour démarrer, sur le nœud de calcul sélectionné (N), le traitement de la charge de travail de la ou des applications logicielles (400).
PCT/EP2020/054978 2019-03-04 2020-02-26 Système et procédé de découverte et d'identification de nœuds de calcul dans un réseau Ceased WO2020178091A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080018594.2A CN113518974B (zh) 2019-03-04 2020-02-26 用于找出并标识网络中的计算节点的系统和方法
US17/435,815 US11669373B2 (en) 2019-03-04 2020-02-26 System and method for finding and identifying computer nodes in a network

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP19160453.7 2019-03-04
EP19160453.7A EP3705993B1 (fr) 2019-03-04 2019-03-04 Système et procédé de détection et d'identification des n uds de calcul dans un réseau

Publications (1)

Publication Number Publication Date
WO2020178091A1 true WO2020178091A1 (fr) 2020-09-10

Family

ID=65817719

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2020/054978 Ceased WO2020178091A1 (fr) 2019-03-04 2020-02-26 Système et procédé de découverte et d'identification de nœuds de calcul dans un réseau

Country Status (4)

Country Link
US (1) US11669373B2 (fr)
EP (1) EP3705993B1 (fr)
CN (1) CN113518974B (fr)
WO (1) WO2020178091A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12321732B2 (en) * 2021-08-10 2025-06-03 Keross Fz-Llc Extensible platform for orchestration of data using probes
US12417105B2 (en) 2021-08-10 2025-09-16 Keross Fz-Llc Extensible platform for orchestration of data with built-in scalability and clustering

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140196054A1 (en) 2013-01-04 2014-07-10 International Business Machines Corporation Ensuring performance of a computing system
US20180129495A1 (en) 2008-12-05 2018-05-10 Amazon Technologies, Inc. Elastic application framework for deploying software

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6298340B1 (en) * 1999-05-14 2001-10-02 International Business Machines Corporation System and method and computer program for filtering using tree structure
GB2367721B (en) * 2000-10-06 2004-03-03 Motorola Inc Network management system and method of management control in a communication system
US7496655B2 (en) * 2002-05-01 2009-02-24 Satyam Computer Services Limited Of Mayfair Centre System and method for static and dynamic load analyses of communication network
US8468581B2 (en) * 2009-03-18 2013-06-18 Savemeeting, S.L. Method and system for the confidential recording, management and distribution of meetings by means of multiple electronic devices with remote storage
US8423962B2 (en) * 2009-10-08 2013-04-16 International Business Machines Corporation Automated test execution plan generation
CN102143022B (zh) * 2011-03-16 2013-09-25 北京邮电大学 用于ip网络的云测量装置和测量方法
US8881136B2 (en) * 2012-03-13 2014-11-04 International Business Machines Corporation Identifying optimal upgrade scenarios in a networked computing environment
US9152532B2 (en) * 2012-08-07 2015-10-06 Advanced Micro Devices, Inc. System and method for configuring a cloud computing system with a synthetic test workload
CN102801587B (zh) * 2012-08-29 2014-09-17 北京邮电大学 面向大规模网络的虚拟化监测系统与动态监测方法
US10069903B2 (en) * 2013-04-16 2018-09-04 Amazon Technologies, Inc. Distributed load balancer
US20150023188A1 (en) * 2013-07-16 2015-01-22 Azimuth Systems, Inc. Comparative analysis of wireless devices
US9817884B2 (en) * 2013-07-24 2017-11-14 Dynatrace Llc Method and system for real-time, false positive resistant, load independent and self-learning anomaly detection of measured transaction execution parameters like response times
CN104360941A (zh) * 2014-11-06 2015-02-18 浪潮电子信息产业股份有限公司 采用MPI与OpenMP编译提高计算集群的STREAM Benchmark测试性能的方法
US9852050B2 (en) * 2014-12-30 2017-12-26 Vmware, Inc. Selecting computing resources
CN106020950B (zh) * 2016-05-12 2019-08-16 中国科学院软件研究所 基于复杂网络分析的函数调用图关键节点识别和标识方法
US10909022B2 (en) * 2017-09-12 2021-02-02 Facebook, Inc. Systems and methods for identifying and tracking application performance incidents

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180129495A1 (en) 2008-12-05 2018-05-10 Amazon Technologies, Inc. Elastic application framework for deploying software
US20140196054A1 (en) 2013-01-04 2014-07-10 International Business Machines Corporation Ensuring performance of a computing system

Also Published As

Publication number Publication date
EP3705993B1 (fr) 2021-07-21
CN113518974B (zh) 2025-04-01
US20220091887A1 (en) 2022-03-24
EP3705993A1 (fr) 2020-09-09
CN113518974A (zh) 2021-10-19
US11669373B2 (en) 2023-06-06

Similar Documents

Publication Publication Date Title
DE112016005536T5 (de) Bestimmen von reihenfolgen einer ausführung eines neuronalen netzes
DE112012005030T5 (de) Dynamisch konfigurierbare Platzierungs-Engine
DE102018109195A1 (de) Diagnosesystem und Verfahren zum Verarbeiten von Daten eines Kraftfahrzeugs
DE112021001648T5 (de) Prioritätsbestimmungssystem, Prioritätsbestimmungsverfahren und Programm
WO2020178091A1 (fr) Système et procédé de découverte et d'identification de nœuds de calcul dans un réseau
WO2023217419A1 (fr) Procédé de réalisation de tâches de traitement de données
EP1624614B1 (fr) Planification automatique des configurations de réseau
DE102021133854A1 (de) Verfügbarmachen von Funktionen an einem Fahrzeug
DE102019217015A1 (de) Kommunikationsvorrichtung
DE102018123563B4 (de) Verfahren zur Zwischenkernkommunikation in einem Mehrkernprozessor
EP3716578B1 (fr) Procédé et dispositif de commande d'un appareil technique à l'aide d'un modèle optimal
DE102021125498A1 (de) Systemvalidierung mit verbesserter Handhabung von Protokollierungsdaten
EP2329374A1 (fr) Module de test et procédé destiné à tester un intergiciel de mapping o/r
DE112016005363T5 (de) Verteilte betriebssystemfunktionen für knoten in einem rack
DE102018219852A1 (de) Verfahren und Vorrichtung zum Ermitteln einer Systemkonfiguration für ein verteiltes System
EP1054528B1 (fr) Méthode pour traiter une demande des appareillages de gestion de réseau
DE102019213738A1 (de) Software-Komponenten für eine Software-Architektur
DE102022109180B4 (de) Einheitliche-policy-broker
EP3796161A1 (fr) Procédé de détermination d'une configuration de conteneur d'un système, système, programme informatique et support lisible par ordinateur
DE102022205835A1 (de) Verfahren zum Zuordnen von wenigstens einem Algorithmus des maschinellen Lernens eines Ensemble-Algorithmus des maschinellen Lernens zu einem von wenigstens zwei Rechenknoten zur Ausführung
DE102025130535A1 (de) Verfahren, domänencontroller und computerprogrammprodukt zur verarbeitung von aktivitäten
DE102023126862A1 (de) Systeme und verfahren zum identifizieren und warnen vor stellflächen-überzyklus-risiken bei allgemeinen mehrprodukt-montagelinien
DE102012214500B4 (de) Zustandsbasierte Planung, Absicherung und Management von Ressourcen einer Datennetzstruktur
DE102017222292B4 (de) Parallelisierungsverfahren und parallelisierungs-tool
DE102023209198A1 (de) System und Verfahren zur automatischen Ausführung einer Migration und Portabilität einer Legacy-Anwendungssoftware

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20710790

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20710790

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 202080018594.2

Country of ref document: CN